Comments (3)
The visual feature representation obtained by MSG3D is 384 dimensional, whereas the one obtained by 4s-ShiftGCN is 256 dimensional. The pretrained models currently provided are trained using 4s-ShiftGCN. I can provide the pretrained model with MSG3D embeddings in the next few days, meanwhile you can try to reproduce the results by training synse from scratch using MSG3D embeddings.
from synse-zsl.
That would definetly be helpful, thank you
from synse-zsl.
Hey, please find the trained msg3d model here.
Place the above directory in the /synse_resources/language_modelling/
directory.
To run the zsl evaluation.
python synse_training.py --ntu 60 --phase train --ss 5 --st r --dataset './synse_resources/ntu_results/msg3d_5_r/' --wdir './synse_resources/language_modelling/synse_msg3d_5_r' --le bert --ve msg3d --num_cycles 10 --load_classifier --num_epoch_per_cycle 1700 --latent_size 100 --load_epoch 8499 --mode eval --gpu 0
Please let me know if there are more issues with the same.
from synse-zsl.
Related Issues (14)
- Rename num_epoch_per_cycle to num_cycle_per_epoch HOT 1
- Extra spaces in examples HOT 1
- [Question] Why did ShiftGCN perform so much better than MS-G3D? HOT 1
- RuntimeError: DataLoader worker (pid(s) 27447) exited unexpectedly HOT 3
- [Questions] Only calling Dataloader once per epoch? Training classifier from scratch at each cycle? HOT 1
- What is gtest_out.npy? HOT 7
- In synse_resources rs10.npy == rs100.npy HOT 2
- What is synse_10_r_unseen_zs.npy and synse_10_r_seen_zs.npy HOT 5
- Confused about some folders HOT 7
- some questions about visual feature extractor HOT 5
- Is there any Inference to test on an Image or a video? HOT 2
- NTU split
- What is val*.npy, where does it come from, and how do you determined the sample size of it?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from synse-zsl.